Kmedoids_clusterN(dt)
## Loading required package: Matrix
##
## Attaching package: 'Matrix'
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack
error and time series representors both
don’t have clusters. There are one dense area and some sparse
points.forecast and accuracy representors can see
clear clusters.The below figure visualizes a euclidean distance matrix of time series.
visualizeDistance(dt_orig, "ts", "euclidean")
visualizeDistance(dt_orig, "error", "dtw")
visualizeDistance(dt_orig, "forecast", "euclidean")
visualizeDistance(dt_orig, "accuracy", "euclidean")
# Group Visualize
visualizeGroup(dt_orig, "accuracy", "euclidean", names = dt_names)
visualizeGroup(dt_orig, "forecast", "euclidean", names = dt_names)
summary(silhouette(pam(dt_orig$distance$ts$euclidean, diss=TRUE, k=2)))
## Silhouette of 304 units in 2 clusters from pam(x = dt_orig$distance$ts$euclidean, k = 2, diss = TRUE) :
## Cluster sizes and average silhouette widths:
## 172 132
## 0.08506153 0.02771729
## Individual silhouette widths:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -0.04200 0.01458 0.03447 0.06016 0.09480 0.23971
clusGap(t(representator.ts(dt_orig)), pam, K.max = 20)
## Clustering Gap statistic ["clusGap"] from call:
## clusGap(x = t(representator.ts(dt_orig)), FUNcluster = pam, K.max = 20)
## B=100 simulated reference sets, k = 1..20; spaceH0="scaledPCA"
## --> Number of clusters (method 'firstSEmax', SE.factor=1): 3
## logW E.logW gap SE.sim
## [1,] 7.333995 7.888536 0.5545410 0.003083401
## [2,] 7.301210 7.877105 0.5758943 0.004615531
## [3,] 7.284371 7.868750 0.5843791 0.004118626
## [4,] 7.276279 7.861660 0.5853812 0.004007524
## [5,] 7.270019 7.855084 0.5850655 0.003648205
## [6,] 7.261755 7.849237 0.5874822 0.003468951
## [7,] 7.254570 7.843358 0.5887877 0.003597396
## [8,] 7.249161 7.837910 0.5887487 0.003436964
## [9,] 7.242896 7.832425 0.5895290 0.003279700
## [10,] 7.236661 7.827282 0.5906213 0.003254337
## [11,] 7.231898 7.821979 0.5900812 0.003360779
## [12,] 7.224934 7.816943 0.5920087 0.003314935
## [13,] 7.218146 7.812012 0.5938663 0.003401122
## [14,] 7.212566 7.807062 0.5944960 0.003441033
## [15,] 7.207370 7.802136 0.5947660 0.003435307
## [16,] 7.202917 7.797240 0.5943230 0.003360371
## [17,] 7.195817 7.792535 0.5967181 0.003429480
## [18,] 7.190615 7.787596 0.5969809 0.003380901
## [19,] 7.183623 7.782825 0.5992028 0.003346182
## [20,] 7.176798 7.778073 0.6012746 0.003349642
summary(silhouette(pam(dt_orig$distance$error$euclidean, diss=TRUE, k=2)))
## Silhouette of 304 units in 2 clusters from pam(x = dt_orig$distance$error$euclidean, k = 2, diss = TRUE) :
## Cluster sizes and average silhouette widths:
## 167 137
## 0.006938547 0.004954501
## Individual silhouette widths:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -0.010820 0.001458 0.004883 0.006044 0.010209 0.058709
avg_measure_fn(dt, metric = "rmsse") %>% arrange(total)
rank_compare(dt)
## Warning: Using an external vector in selections was deprecated in tidyselect 1.1.0.
## ℹ Please use `all_of()` or `any_of()` instead.
## # Was:
## data %>% select(measure)
##
## # Now:
## data %>% select(all_of(measure))
##
## See <https://tidyselect.r-lib.org/reference/faq-external-vector.html>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo